Literature DB >> 23289478

Computer-assisted, atlas-based segmentation for target volume delineation in whole pelvic IMRT for prostate cancer.

Sunanda Pejavar1, Sue S Yom, Andrew Hwang, Joycelyn Speight, Alexander Gottschalk, I-Chow Hsu, Mack Roach, Ping Xia.   

Abstract

The purpose of this study is to evaluate whether computer-assisted segmentation is clinically feasible in target volume delineation for prostate cancer patients treated with whole pelvic IMRT. An atlas was created, comprised of 44 clinically node-negative prostate cancer patients. Three regions of interest (ROIs) were chosen for analysis: prostate, pelvic lymph nodes, and rectum. For a separate tester set of 15 patients with previously contoured ROIs by three experienced physicians, atlas-assisted contours were compared to manual contours by calculating a volumetric overlap index. In the tester set patients, the average overlap between the manually drawn and atlas-based contours for the prostate, pelvic lymph nodes, and rectum was 60%, 51%, and 64%, respectively. The volume differences were significant in the rectum and pelvic lymph nodes (p = 0.049 and p = 0.016, respectively); this was not true for the prostate. A subset analysis based on physician-specific atlases showed that the average overlap index for the pelvic lymph nodal volume increased from 51% to 60%, while the other ROIs had no significant changes. Despite significant inter-physician differences, atlas-based segmentation for pelvic lymph node delineation serves as an initial guideline for physicians, potentially improving both consistency and efficiency in contouring.

Entities:  

Mesh:

Year:  2012        PMID: 23289478     DOI: 10.7785/tcrt.2012.500313

Source DB:  PubMed          Journal:  Technol Cancer Res Treat        ISSN: 1533-0338


  6 in total

1.  Evaluation and optimization of the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy.

Authors:  Wicger K H Wong; Lucullus H T Leung; Dora L W Kwong
Journal:  Br J Radiol       Date:  2015-11-05       Impact factor: 3.039

2.  SPARSE: Seed Point Auto-Generation for Random Walks Segmentation Enhancement in medical inhomogeneous targets delineation of morphological MR and CT images.

Authors:  Haibin Chen; Xin Zhen; Xuejun Gu; Hao Yan; Laura Cervino; Yang Xiao; Linghong Zhou
Journal:  J Appl Clin Med Phys       Date:  2015-03-08       Impact factor: 2.102

3.  Atlas-based auto-segmentation for postoperative radiotherapy planning in endometrial and cervical cancers.

Authors:  Nalee Kim; Jee Suk Chang; Yong Bae Kim; Jin Sung Kim
Journal:  Radiat Oncol       Date:  2020-05-13       Impact factor: 3.481

4.  Evaluation of deep learning-based auto-segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients.

Authors:  Zhi Wang; Yankui Chang; Zhao Peng; Yin Lv; Weijiong Shi; Fan Wang; Xi Pei; X George Xu
Journal:  J Appl Clin Med Phys       Date:  2020-11-25       Impact factor: 2.102

5.  Methodological approach to create an atlas using a commercial auto-contouring software.

Authors:  Marta Casati; Stefano Piffer; Silvia Calusi; Livia Marrazzo; Gabriele Simontacchi; Vanessa Di Cataldo; Daniela Greto; Isacco Desideri; Marco Vernaleone; Giulio Francolini; Lorenzo Livi; Stefania Pallotta
Journal:  J Appl Clin Med Phys       Date:  2020-11-25       Impact factor: 2.102

6.  Clinical validation of an automatic atlas-based segmentation tool for male pelvis CT images.

Authors:  Marta Casati; Stefano Piffer; Silvia Calusi; Livia Marrazzo; Gabriele Simontacchi; Vanessa Di Cataldo; Daniela Greto; Isacco Desideri; Marco Vernaleone; Giulio Francolini; Lorenzo Livi; Stefania Pallotta
Journal:  J Appl Clin Med Phys       Date:  2022-01-22       Impact factor: 2.102

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.